© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35723
    Prev
    Next
    INDEX
    Explanations

    quotes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Catch
    0.40
    čí
    0.39
     neat
    0.36
    칫
    0.36
     `--
    0.35
    Invariant
    0.35
     Corporal
    0.35
     ser
    0.35
    Lie
    0.35
    oken
    0.34
    POSITIVE LOGITS
     Tyrone
    0.44
    াচ্ছে
    0.41
    喀
    0.41
    Amber
    0.41
    ٹا
    0.40
     Roh
    0.39
    TOG
    0.39
     रघु
    0.39
     Cora
    0.39
     അംഗ
    0.39
    Activations Density 0.001%

    No Known Activations